Bluetooth earphone anti-interference performance test system

Abstract

The invention relates to an anti-interference performance test system for a Bluetooth headset, and relates to the technical field of data processing, and the system comprises an environment parameter module which is used for obtaining initial interference environment parameters; the scene parameter module is used for generating composite interference scene parameters; the feature extraction module is used for extracting human body dynamic interference features according to the composite interference scene parameters; the link evaluation module is used for obtaining link quality evaluation data based on the human body dynamic interference characteristics; the audio evaluation module is used for calling an audio quality evaluation model based on deep learning based on the link quality evaluation data, calculating a dynamic audio quality score and obtaining an audio performance evaluation result; and the test optimization module is used for calculating an interference adaptability index based on the audio performance evaluation result and outputting optimization suggestion data. The system can improve the anti-interference test effect of the Bluetooth headset.

Description

Technical Field

[0001] This invention relates to the field of Bluetooth headset technology, and in particular to a Bluetooth headset anti-interference performance testing system. Background Technology

[0002] With the widespread application of wireless communication technology, Bluetooth headsets have become an important component of portable audio devices, widely used in scenarios such as calls, music playback, and voice interaction. Existing testing methods for the anti-interference performance of Bluetooth headsets mainly involve introducing wireless interference sources (such as Wi-Fi signals, other Bluetooth devices, microwave ovens, etc.) with fixed frequencies and power in shielded rooms or open spaces, measuring the headset's signal connection stability, audio quality, and data packet loss rate under different interference environments. These methods typically rely on traditional channel simulators, transmit power control equipment, and standardized audio quality evaluation tools, such as PESQ (Perceptual Evaluation of Speech Quality) or MOS (Mean Opinion Score).

[0003] However, existing test scenarios are relatively limited and cannot realistically simulate interference characteristics under multi-source interference, dynamic scenarios, and complex environments (such as subways, shopping malls, and office buildings). Furthermore, most test methods lack dynamic control over the location, mobility, and intensity of interference sources, making it difficult to reflect the robustness of Bluetooth headsets against sudden and multi-band cross-interference in real-world use. In addition, existing test methods typically do not fully consider the performance impact of built-in sensors in Bluetooth headsets (such as accelerometers and gyroscopes) in dynamic environments, such as signal stability and anti-interference capabilities during motion, which further limits the comprehensiveness and realism of the test results. Summary of the Invention

[0004] This invention addresses the technical problems existing in the prior art by providing a Bluetooth headset anti-interference performance testing system, method, electronic device, and non-transitory computer-readable storage medium that can improve the anti-interference test effect of Bluetooth headsets.

[0005] The technical solution of the present invention to solve the above-mentioned technical problems is as follows: This invention provides a Bluetooth headset anti-interference performance testing system, the system comprising: The environmental parameter module is used to construct a multi-dimensional interference source matrix. It controls multiple interference sources to be dynamically deployed in three-dimensional space through a programmable robotic arm, forming an electromagnetic interference environment with adjustable interference intensity and spatial distribution, and obtaining initial interference environment parameters. The scene parameter module is used to construct an environmental acoustic characteristic simulation system based on the initial interference environment parameters. By adjusting the loudspeaker array and variable acoustic materials, it simulates the acoustic noise characteristics of the usage environment and generates composite interference scene parameters. The feature extraction module is used to control a bionic human model with human electromagnetic properties to perform preset dynamic actions based on the parameters of the composite interference scenario, and to collect data on the absorption and reflection of Bluetooth signals by the bionic model in real time to extract human dynamic interference features. The link evaluation module is used to collect link parameters in real time during Bluetooth communication based on the human body dynamic interference characteristics using a non-invasive Bluetooth link quality monitoring system, and compare the link parameters with preset benchmark performance indicators to obtain link quality evaluation data. The audio evaluation module is used to call a deep learning-based audio quality evaluation model based on the link quality evaluation data to calculate a dynamic audio quality score and obtain audio performance evaluation results. The test optimization module is used to calculate the interference adaptability index based on the audio performance evaluation results and output optimization suggestion data.

[0006] Optionally, the environmental parameter module is also used for: Based on the three-dimensional deployment location and emission parameters of each interference source, corresponding spatial distribution parameters are generated; Based on the operating frequency band characteristics and transmission power of the interference source, calculate the corresponding electromagnetic interference intensity parameters; The spatial distribution parameters and the electromagnetic interference intensity parameters are input into a preset interference superposition model, and the initial interference environment parameters are output.

[0007] Optionally, the scene parameter module is further used for: Based on the initial interference environment parameters, the sound pressure level and frequency distribution of the loudspeaker array are controlled to generate traffic noise characteristic parameters; Based on the traffic noise characteristic parameters, acoustic environment parameters are generated by adjusting the acoustic reflection coefficient of the variable acoustic material. The traffic noise characteristic parameters and the acoustic environment parameters are input into the environmental noise superposition algorithm to output the composite interference scene parameters.

[0008] Optionally, the feature extraction module is further used for: Based on a preset dynamic action sequence, motion data of a bionic human model is collected, and corresponding motion feature parameters are generated. The motion characteristic parameters are input into the conductivity model to calculate the absorption and reflection rates of Bluetooth signals by the human body. Based on the absorption rate and the reflectivity, the dynamic interference characteristics of the human body are output through a signal interference model.

[0009] Optionally, the link evaluation module is further used for: The link parameters are collected in real time; Based on the link parameters, calculate the data packet loss rate and retransmission rate of the Bluetooth link; The packet loss rate and the retransmission rate are input into the link quality scoring model, and the link quality assessment data is output.

[0010] Optionally, the audio evaluation module is also used for: Obtain a training dataset containing reference audio samples from normal environments and test audio samples from interfering environments. The deep learning model is trained based on the training dataset. During training, a preset loss function, including an error term for audio quality indicators and a jitter penalty term, is used to optimize the model parameters to obtain the dynamic audio quality score.

[0011] Optionally, the test optimization module is further used for: Obtain performance metrics in various test scenarios; The performance indicators are normalized to generate standardized performance data; The standardized performance data is input into a time response model for calculation to obtain the interference adaptability index.

[0012] Optionally, the test optimization module is further used for: Based on the performance bottleneck identification report, extract the abnormal parameters from the link quality assessment data; Based on the abnormal parameters, a corresponding improvement scheme is matched in the preset optimization strategy library; The improved scheme is combined with the interference adaptability index to generate the optimization suggestion data.

[0013] Optionally, the system further includes: A full-band signal acquisition module for capturing Bluetooth communication signals in the 2.4GHz and 5GHz frequency bands; The real-time decoding module is used to extract data packet loss rate, frequency hopping behavior and signal strength change information from the Bluetooth communication signal; The comparative analysis module is used to compare the decoding results with benchmark performance indicators and output the link quality assessment data.

[0014] Optionally, the bionic human model is also used for: A conductive framework structure that simulates the electromagnetic properties of human tissue; Simulates micro-movements of the human head, hand touch control, and full-body movement; A sensor array that collects motion data and signal absorption and reflection information in real time.

[0015] The present invention also provides a method for testing the anti-interference performance of Bluetooth headsets, the method comprising: A multi-dimensional interference source matrix is ​​constructed, and multiple interference sources are dynamically deployed in three-dimensional space by a programmable robotic arm to form an electromagnetic interference environment with adjustable interference intensity and spatial distribution, and to obtain initial interference environment parameters. Based on the initial interference environment parameters, an environmental acoustic characteristic simulation system is constructed. By adjusting the loudspeaker array and variable acoustic materials, the acoustic noise characteristics of the usage environment are simulated to generate composite interference scene parameters. Based on the parameters of the composite interference scenario, the bionic human model with human electromagnetic properties is controlled to perform preset dynamic actions, and the absorption and reflection data of the bionic model to Bluetooth signals are collected in real time to extract the dynamic interference characteristics of the human body. Based on the aforementioned human dynamic interference characteristics, a non-invasive Bluetooth link quality monitoring system is used to collect link parameters in real time during Bluetooth communication, and the link parameters are compared with preset benchmark performance indicators to obtain link quality evaluation data. Based on the link quality assessment data, a deep learning-based audio quality assessment model is invoked to calculate the dynamic audio quality score and obtain the audio performance assessment result. Based on the audio performance evaluation results, the interference adaptability index is calculated, and optimization suggestion data is output.

[0016] Furthermore, to achieve the above objectives, the present invention also proposes an electronic device, comprising: a memory for storing computer software programs; and a processor for reading and executing the computer software programs, thereby realizing the Bluetooth headset anti-interference performance testing method described above.

[0017] Furthermore, to achieve the above objectives, the present invention also proposes a non-transitory computer-readable storage medium storing a computer software program, which, when executed by a processor, implements a Bluetooth headset anti-interference performance testing method as described above.

[0018] The beneficial effects of this invention are: (1) By constructing a three-dimensional interference matrix containing multiple frequency band interference sources such as Wi-Fi, Bluetooth, microwave, and electromagnetic, and introducing an acoustic simulation system, this invention can highly reproduce typical high-interference environments such as subways, offices, and shopping malls. Compared with existing test schemes that mainly use a single static interference source, this invention can cover a wider range of practical application scenarios, and the test results are more representative and have greater application value.

[0019] (2) All interference sources in this invention are dynamically scheduled in three dimensions through a programmable robotic arm, which can achieve precise control of the position, direction and intensity of the interference sources, meet the test requirements for dynamic interference switching, and simulate dynamic processes such as user movement between different scenarios and rapid changes in interference sources, effectively evaluating the link stability and adaptive capability of the headphones.

[0020] (3) This invention introduces a bionic human body model with conductive properties and simulates the influence of the human body on signal propagation during real use by head and hand movements, thereby improving the realism of channel environment modeling. It can measure and quantify absorption rate and reflectivity, and make up for the link performance fluctuation problem caused by “human body occlusion and interference” that cannot be evaluated by traditional no-load testing.

[0021] In summary, this invention effectively solves the problems existing in the anti-interference performance testing of built-in sensors in Bluetooth headsets, such as limited testing scenarios, lack of dynamic control, inability to reflect real-world usage situations, and subjective evaluation mechanisms. It provides an efficient, reliable, and intelligent testing method for evaluating and optimizing the anti-interference capabilities of wireless audio devices, and has significant technical value and application prospects. Attached Figure Description

[0022] Figure 1 A scenario diagram illustrating a Bluetooth headset anti-interference performance testing method provided by this invention; Figure 2 This invention provides a schematic diagram of the structure of a Bluetooth headset anti-interference performance testing system. Figure 3 A flowchart of a Bluetooth headset anti-interference performance testing method provided by the present invention; Figure 4 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention; Figure 5 This is a schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0025] In the description of this invention, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein.

[0026] Please see Figure 1 , Figure 1 This is a scenario diagram illustrating a Bluetooth headset anti-interference performance testing method provided by the present invention. Figure 1 As shown, the terminal and server are connected via a network, such as a wired or wireless network. The terminal can include, but is not limited to, portable devices such as mobile phones and tablets with various network platform applications installed, as well as fixed terminals such as computers, kiosks, and advertising machines. The server provides users with various business services, including service push servers and user recommendation servers.

[0027] It should be noted that, Figure 1 The scenario diagram illustrating a Bluetooth headset anti-interference performance testing method is merely an example. The terminals, servers, and application scenarios described in this embodiment are for the purpose of more clearly illustrating the technical solutions of this embodiment and do not constitute a limitation on the technical solutions provided by this embodiment. As those skilled in the art will know, with the evolution of systems and the emergence of new business scenarios, the technical solutions provided by this embodiment are also applicable to similar technical problems.

[0028] The terminal can be used for: A multi-dimensional interference source matrix is ​​constructed, and multiple interference sources are dynamically deployed in three-dimensional space by a programmable robotic arm to form an electromagnetic interference environment with adjustable interference intensity and spatial distribution, and to obtain initial interference environment parameters. Based on the initial interference environment parameters, an environmental acoustic characteristic simulation system is constructed. By adjusting the loudspeaker array and variable acoustic materials, the acoustic noise characteristics of the usage environment are simulated to generate composite interference scene parameters. Based on the parameters of the composite interference scenario, the bionic human model with human electromagnetic properties is controlled to perform preset dynamic actions, and the absorption and reflection data of the bionic model to Bluetooth signals are collected in real time to extract the dynamic interference characteristics of the human body. Based on the aforementioned human dynamic interference characteristics, a non-invasive Bluetooth link quality monitoring system is used to collect link parameters in real time during Bluetooth communication, and the link parameters are compared with preset benchmark performance indicators to obtain link quality evaluation data. Based on the link quality assessment data, a deep learning-based audio quality assessment model is invoked to calculate the dynamic audio quality score and obtain the audio performance assessment result. Based on the audio performance evaluation results, the interference adaptability index is calculated, and optimization suggestion data is output.

[0029] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of a Bluetooth headset anti-interference performance testing system provided by the present invention.

[0030] like Figure 2 As shown in the figure, the Bluetooth headset anti-interference performance testing system proposed in this embodiment of the invention includes: The environmental parameter module 201 is used to construct a multi-dimensional interference source matrix. It controls multiple interference sources to be dynamically deployed in three-dimensional space through a programmable robotic arm, forming an electromagnetic interference environment with adjustable interference intensity and spatial distribution, and obtaining initial interference environment parameters.

[0031] In this embodiment, multiple electromagnetic interference sources are first arranged in a shielded test chamber, including a 2.4GHz / 5GHz dual-band Wi-Fi signal generator, a multi-band Bluetooth interference simulator, a microwave oven electromagnetic radiation simulator, and a wireless video transmission equipment simulator. Each interference source is installed at the end of a programmable 3D robotic arm, and its relative position, height, and orientation in space are set through a motion control program to achieve dynamic adjustment of the spatial distribution of the interference sources. Simultaneously, the transmission power, channel configuration, and operating mode of each interference source are independently adjusted through a radio frequency signal controller. Based on a preset test scenario, the system automatically configures the combination and spatial layout of the interference sources and performs preliminary measurements of the electromagnetic field distribution within the test area using a field strength scanner. This generates initial interference environment parameters containing interference type, spatial coordinates, transmission intensity, and frequency band information, which serve as input for subsequent environmental simulations.

[0032] The scene parameter module 202 is used to construct an environmental acoustic characteristic simulation system based on the initial interference environment parameters. By adjusting the loudspeaker array and variable acoustic materials, it simulates the acoustic noise characteristics of the usage environment and generates composite interference scene parameters.

[0033] After obtaining the initial interference environment parameters, the environmental acoustic characteristic simulation system is activated. This system includes a multi-channel speaker array arranged around the perimeter and adjustable acoustic absorption / reflection panels on the walls. Based on the test scenario set in step 301 (such as a subway, shopping mall, or office environment), the system calls upon the corresponding noise sample library and controls the speakers to play background noise with specific spectral characteristics and sound pressure levels. For example, when simulating a subway environment, a composite sound field dominated by low-frequency vibration noise is played; when simulating a shopping mall environment, mixed noises such as human conversations and advertising broadcasts are superimposed. Simultaneously, the reverberation time and sound reflection characteristics of the test space are adjusted by changing the opening angle and position of the variable acoustic material through an electric adjustment mechanism. The system fuses electromagnetic interference parameters with acoustic parameters to generate composite interference scenario parameters containing both electromagnetic and acoustic interference characteristics, which drive subsequent testing procedures.

[0034] The feature extraction module 203 is used to control a bionic human model with electromagnetic properties to perform preset dynamic actions based on the parameters of the composite interference scene, and to collect data on the absorption and reflection of Bluetooth signals by the bionic model in real time to extract the dynamic interference features of the human body.

[0035] After obtaining the initial interference environment parameters, the environmental acoustic characteristic simulation system is activated. This system includes a multi-channel speaker array arranged around the perimeter and adjustable acoustic absorption / reflection panels on the walls. Based on the test scenario set in step 301 (such as a subway, shopping mall, or office environment), the system calls upon the corresponding noise sample library and controls the speakers to play background noise with specific spectral characteristics and sound pressure levels. For example, when simulating a subway environment, a composite sound field dominated by low-frequency vibration noise is played; when simulating a shopping mall environment, mixed noises such as human conversations and advertising broadcasts are superimposed. Simultaneously, the reverberation time and sound reflection characteristics of the test space are adjusted by changing the opening angle and position of the variable acoustic material through an electric adjustment mechanism. The system fuses electromagnetic interference parameters with acoustic parameters to generate composite interference scenario parameters containing both electromagnetic and acoustic interference characteristics, which drive subsequent testing procedures.

[0036] The link evaluation module 204 is used to collect link parameters in real time during Bluetooth communication based on human dynamic interference characteristics using a non-invasive Bluetooth link quality monitoring system, and compare the link parameters with preset benchmark performance indicators to obtain link quality evaluation data.

[0037] Under the influence of dynamic human interference, a non-invasive Bluetooth link quality monitoring system is activated. This system captures the communication signals between the tested Bluetooth headset and the audio source device using a high-sensitivity broadband receiving antenna. It then uses a protocol analyzer to analyze link-layer data packets in real time, obtaining key link parameters such as packet loss rate, retransmission count, Received Signal Strength Indicator (RSSI), channel hopping sequence, and link control commands. All data is recorded in time-series format and compared item by item with baseline performance indicators measured in an interference-free environment. Based on the degree of difference, the system calculates derived indicators such as link stability score and anti-interference recovery time, ultimately generating link quality assessment data that comprehensively reflects the operating status of the Bluetooth link under dynamic composite interference.

[0038] The audio evaluation module 205 is used to calculate the dynamic audio quality score and obtain the audio performance evaluation result by calling the deep learning-based audio quality evaluation model based on the link quality evaluation data.

[0039] Based on the obtained link quality assessment data, a pre-trained deep learning audio quality assessment model is invoked. This model takes link parameters, the receiver audio signal waveform, and a reference clean audio signal as input, and extracts perceptually relevant features such as spectral distortion, speech intelligibility degradation, playback delay and jitter, and sound interruptions through a convolutional neural network and a temporal modeling module. The model outputs a Dynamic Audio Quality Score (DAQS), which quantifies the degree of degradation in the user's actual listening experience. The system determines the audio quality level based on the score range and generates audio performance assessment results for subsequent comprehensive evaluation.

[0040] The test optimization module 206 is used to calculate the interference adaptability index based on the audio performance evaluation results and output optimization suggestion data.

[0041] Finally, based on the audio performance evaluation results, combined with the degree of performance degradation and recovery response time in each test scenario, the system calculates the Interference Adaptability Index (IAI) to measure the Bluetooth headset's ability to maintain usable audio quality under different interference environments. The system further utilizes its built-in performance bottleneck analysis module, combining link quality, human interference, and audio degradation data to identify key factors causing performance degradation (such as sensitivity to interference in specific frequency bands and slow response to human occlusion), and matches optimization suggestions from aspects such as antenna design, protocol configuration, and audio codec strategies. This generates structured optimization suggestion data, providing a technical basis for product improvement.

[0042] In some embodiments, the environment parameter module 201 is further configured to: Based on the three-dimensional deployment location and transmission parameters of each interference source, corresponding spatial distribution parameters are generated; Based on the operating frequency band characteristics and transmission power of the interference source, calculate the corresponding electromagnetic interference intensity parameters; The spatial distribution parameters and electromagnetic interference intensity parameters are input into the preset interference superposition model, and the initial interference environment parameters are output.

[0043] First, multiple electromagnetic interference sources (such as a 2.4GHz Wi-Fi signal generator, a 5GHz Wi-Fi signal generator, a multi-band Bluetooth interference simulator, a microwave oven electromagnetic radiation simulator, a ZigBee interference simulator, and a wireless video transmission device) are mounted on a programmable robotic arm with six degrees of freedom of motion. Through a preset spatial distribution strategy, the placement (X, Y, Z coordinates) and orientation (pitch angle, yaw angle, roll angle) of each interference source in three-dimensional space are controlled to form a structured spatial interference distribution pattern.

[0044] Subsequently, based on parameters such as the transmission frequency band (e.g., 2.4GHz, 5GHz, 915MHz), modulation method (e.g., Wi-Fi OFDM, Bluetooth BR / EDR, BLE GFSK), transmission power (in dBm), and transmission cycle of each interference source, combined with their spatial deployment information, a spatial distribution parameter model of the interference sources within the test area was established. This model records the theoretical radiation influence range of each interference source on any sampling point within the test area.

[0045] Next, based on the frequency band characteristics and transmit power, the electromagnetic interference intensity parameters generated by each interference source in the target test area are calculated. The modeling is carried out using the following steps: using the free space path loss model or a higher-order three-dimensional multipath attenuation model, the signal attenuation from each interference source to the position of the earphone under test is calculated; considering the interference coupling coefficient and antenna gain correction factor under different frequency bands, the interference power value per unit frequency band (unit dBm / Hz) of each interference source at the target point is obtained; the interference intensity distribution map of each interference source is constructed separately and uniformly mapped to three-dimensional raster data with a uniform spatial resolution.

[0046] Finally, the spatial distribution parameters and the corresponding electromagnetic interference intensity parameters are input into the preset interference superposition model. The model can be based on the linear superposition principle, the interference power weighting model, or the nonlinear fusion network driven by empirical data to comprehensively calculate the equivalent interference energy density, spectral overlap, and instantaneous interference index at each spatial unit or test point, and output the initial interference environment parameter A in a unified format accordingly.

[0047] The initial interference environment parameter A serves as the input for acoustic environment construction, human interference modeling, and link quality evaluation in subsequent testing processes. It features high spatial accuracy, rich parameter dimensions, and dynamic updates, significantly improving the realism and controllability of interference environment simulation.

[0048] In some embodiments, the scene parameter module 202 is further configured to: Based on the initial interference environment parameters, the sound pressure level and frequency distribution of the loudspeaker array are controlled to generate traffic noise characteristic parameters; Based on traffic noise characteristic parameters, acoustic environment parameters are generated by adjusting the acoustic reflection coefficient of variable acoustic materials. Traffic noise characteristic parameters and acoustic environment parameters are input into an environmental noise superposition algorithm to output composite interference scene parameters.

[0049] In one embodiment, to simulate the dynamic noise interference environment in a real-world usage scenario, the system first controls the sound pressure level and frequency distribution of multiple speaker arrays based on the aforementioned initial interference environment parameters. Specifically, the system calculates the sound field coverage of the headphone wearing area at different times, based on the relative position of the interference sources in space, their radiation direction, and their corresponding electromagnetic interference intensity.

[0050] Next, based on the characteristics of common noise sources in urban traffic scenarios (including vehicle acceleration, horn honking, road friction and reverberation characteristics, etc.), the system sets the target output frequency range of the speaker array (such as low-frequency engine noise <500Hz and high-frequency braking sound >2kHz), and dynamically adjusts the sound pressure level to match the intensity changes of typical traffic noise at different times, generating traffic noise characteristic parameters that characterize a specific traffic sound environment.

[0051] Furthermore, based on the aforementioned traffic noise characteristic parameters, the material state of the adjustable acoustic interfaces (such as variable structure foam walls, acoustic response curtains, etc.) within the experimental chamber is controlled. The system adjusts the acoustic reflection coefficients of these variable acoustic materials to simulate the reverberation characteristics and absorption properties of different sound fields, such as enclosed carriages, open roads, and tunnels, generating corresponding acoustic environment parameters.

[0052] Finally, the aforementioned traffic noise characteristic parameters and acoustic environment parameters are input into a preset environmental noise superposition algorithm. This algorithm, based on finite element acoustic simulation and a multi-channel reverberation model, calculates the interference superposition effect of multi-source noise in complex environments and outputs composite interference scene parameters describing the overall sound field distribution and time-frequency dynamic characteristics of the current test environment, serving as the input benchmark for subsequent anti-interference performance testing and sound quality analysis.

[0053] In some embodiments, the feature extraction module 203 is further configured to: Based on a preset dynamic action sequence, motion data of a bionic human model is collected, and corresponding motion feature parameters are generated. The motion characteristic parameters are input into the conductivity model to calculate the absorption and reflection rates of Bluetooth signals by the human body. Based on absorptivity and reflectivity, the dynamic interference characteristics of the human body are output through a signal interference model.

[0054] In one specific embodiment, to simulate the interference effect of human movement on Bluetooth signals in real-world usage scenarios, the system presets a set of dynamic motion sequences. These sequences cover typical user movement patterns while wearing headphones, such as head rotation, shoulder swinging, arm waving, and shaking during running. The motion sequences are executed by driving a bionic human model with multi-degree-of-freedom joints. During execution, continuous three-dimensional spatial motion data is collected using inertial measurement units (IMUs) and flexible displacement sensors integrated into key parts of the bionic human model. Based on this data, corresponding motion characteristic parameters are generated, including but not limited to: limb swing amplitude, velocity vector, relative displacement, and rate of change of acceleration.

[0055] Subsequently, the motion characteristic parameters are input into a preset conductivity model. This model comprehensively considers factors such as the surface conductivity of human skin, tissue composition, water content, wearing position, and posture angle to calculate the absorption rate (α) and reflectivity (β) of the bionic model for Bluetooth radio frequency signals under specific posture and dynamic conditions. The absorption rate represents the proportion of signal energy absorbed by human tissue, and the reflectivity represents the proportion of signal bounce caused by surface irregularities or structural abrupt changes; both dynamically change with time and movement rhythm.

[0056] Furthermore, the system inputs the absorption rate and reflectivity parameters into the constructed signal interference model, and performs interference superposition analysis by combining each physical channel in the Bluetooth communication protocol (such as the frequency offset tolerance after GFSK modulation, transmission window, etc.), and outputs the corresponding human dynamic interference characteristic parameters to characterize the degree of influence of the bionic human body on the Bluetooth signal quality under multiple actions and postures.

[0057] This process enables accurate modeling and real-time feedback of human dynamic characteristics on wireless communication interference, providing key interference source inputs for subsequent interference robustness assessment.

[0058] In some embodiments, the link evaluation module 204 is further configured to: Real-time acquisition of link parameters; Calculate the packet loss rate and retransmission rate of the Bluetooth link based on the link parameters; Input the packet loss rate and retransmission rate into the link quality scoring model, and output link quality assessment data.

[0059] In this embodiment, the system first collects the link parameters of the target headphone device in real time during the test through the Bluetooth protocol stack interface. The link parameters include, but are not limited to, Received Signal Strength Indicator (RSSI), link latency, link jitter, channel utilization, and connection stability indicators.

[0060] Subsequently, based on the collected link parameters, the system uses statistical analysis methods to calculate the data packet loss rate and data packet retransmission rate of the target earphone within a specified test time window. The data packet loss rate refers to the proportion of data packets sent but not successfully received per unit time to the total number of sent packets; the data packet retransmission rate refers to the proportion of data packets retransmitted due to reception failure to the total number of sent packets.

[0061] The system further uses the packet loss rate and retransmission rate as input variables and inputs them into a preset link quality scoring model. The scoring model is constructed based on a weighted modulation function or a multi-factor regression algorithm, which can integrate multi-dimensional link degradation indicators and output quantitative link quality assessment data.

[0062] Ultimately, the link quality assessment data can be used to determine the anti-interference performance level of Bluetooth headsets under different dynamic interference scenarios, providing quantitative support for subsequent comprehensive scoring.

[0063] In some embodiments, the audio evaluation module 205 is further configured to: Obtain a training dataset containing reference audio samples from normal environments and test audio samples from interfering environments. Train the deep learning model based on the training dataset; During training, a preset loss function that includes an error term for audio quality metrics and a jitter penalty term is used to optimize the model parameters to obtain a dynamic audio quality score.

[0064] In this embodiment, the system first acquires an audio sample dataset for training. The training dataset includes reference audio samples in a normal environment and test audio samples in an interference environment. The normal environment audio samples are standard audio signals collected under conditions without external interference sources, while the interference environment audio samples are real audio signals collected in simulated dynamic multi-source interference scenarios (such as human body occlusion, environmental reflection, and cross-interference of devices).

[0065] Subsequently, the system performs supervised training on the constructed deep learning audio quality evaluation model based on the training dataset. The model adopts an architecture that combines multi-layer convolutional neural networks with time series processing structures (such as LSTM or Transformer) to enhance the sensitivity to spectral changes and temporal perturbations.

[0066] During model training, the system introduces a joint loss function that includes an error term for sound quality metrics and a jitter penalty term, used for iterative optimization of the model parameters. Specifically: The audio quality metric error term is constructed based on the difference between the target audio quality score (such as the subjective MOS score or objective metrics such as PESQ) and the model output; The jitter penalty term is used to constrain the magnitude of changes in the model's output score across consecutive audio frames, thereby reducing the model's hypersensitivity to short-term fluctuations and improving the stability and robustness of the scoring.

[0067] In some embodiments, the dynamic audio quality score can be expressed as:

[0068] in, It is the dynamic audio quality score. It is the i-th basic sound quality indicator. It is the weight of the i-th sound quality index. It is the scene adaptability coefficient. It is a time-varying jitter function. It is the jitter penalty coefficient. It is the evaluation time window.

[0069] Specifically, The final output dynamic audio quality score is used to comprehensively evaluate the listening experience quality of Bluetooth headphones in specific interference scenarios. The higher the value, the better the sound quality performance. Indicates the first i Basic audio quality metrics include signal-to-noise ratio (SNR), distortion rate (THD), speech clarity (PESQ), and frequency response consistency. In order to be with the first i The weight parameters corresponding to the basic sound quality indicators are determined based on the correlation between subjective sound quality scores and objective measurement results in the training samples, and are used to highlight the contribution of important indicators to the overall score. The scene adaptability coefficient is adjusted based on the audio complexity of the current test scene (such as subway, bus, street, indoor, etc.) to enhance the model's generalization ability to different usage environments. This is a time-varying jitter function used to describe the test audio within the evaluation time window. T The degree of audio playback jitter caused by factors such as unstable link and insufficient anti-interference. The jitter penalty coefficient is used to control the impact of jitter on the overall sound quality score. Its value can be optimized through cross-validation to achieve optimal perceptual consistency. The evaluation time window refers to the effective time interval selected during the audio quality evaluation process, which is usually a few seconds to a dozen seconds, depending on the length of the test task and the user's perception sensitivity.

[0070] This scoring function integrates a static sound quality metric aggregation term with a dynamic jitter penalty term. By introducing integral quantization of temporal perturbations, it significantly improves the accuracy of sound quality evaluation in dynamic scenarios with multiple disturbances. This structure is particularly suitable for objectively evaluating the performance of Bluetooth headphones in high-interference environments such as subway car traffic, high-speed trains, or crowded places, overcoming the limitation of existing methods that rely solely on static metrics and ignore dynamic fluctuations.

[0071] Through the above training strategy, the system can obtain a set of optimized model parameters, thereby realizing the dynamic generation of audio quality scores for the audio output quality of Bluetooth headphones under different interference environments. These scores can be used for subsequent quantitative evaluation and comparative analysis of anti-interference performance.

[0072] In some embodiments, the test optimization module 206 is further configured to: Obtain performance metrics in various test scenarios; The performance metrics are normalized to generate standardized performance data; Standardized performance data is input into a time-response model for calculation to obtain the interference adaptability index.

[0073] In this embodiment, the Bluetooth headset system under test is first run in various preset test scenarios. These test scenarios include, but are not limited to, representative interference environments such as subway cars, highways, shopping malls, offices, and open streets. For each test scenario, multiple performance indicators related to anti-interference performance are collected using a testing device. These performance indicators include, but are not limited to, link stability, audio clarity, latency, packet loss rate, and user subjective listening experience ratings.

[0074] Subsequently, the collected performance indicators are normalized using linear normalization or Z-score standardization methods to convert performance data of different dimensions and scales into dimensionless standardized performance data within a unified range, facilitating subsequent unified processing and analysis.

[0075] The standardized performance data is input into the constructed time response model for calculation. This model comprehensively evaluates the Bluetooth headset's response speed and stability to external interference during changes in the interference environment, based on the changing trends of each performance indicator across different time segments. The model models the dynamic changes of performance indicators before, during, and after interference occurs, outputting a numerical result as the interference adaptability index for this test scenario.

[0076] Ultimately, by combining the interference adaptability index under various test scenarios, we can construct a comprehensive anti-interference capability profile of headphones under different interference environments, providing a basis for product performance optimization, scenario matching, and quality assessment.

[0077] In some embodiments, the interference adaptability index can be expressed as:

[0078] in, It is the interference adaptability index. The headphones are in the first Performance metrics under various interference environments It is a performance indicator under a non-interference benchmark environment. It is the headphones that adapt to interference environments Time required is the baseline adaptation time, k is the time sensitivity coefficient, and M is the total number of interference test scenarios.

[0079] Specifically, IAI (Interference Adaptability Index) represents the overall adaptability of Bluetooth headphones to interference environments; a higher value indicates stronger adaptability. M represents the total number of interference environment scenarios covered in the test. For example, subways, high-speed trains, airports, and densely populated outdoor areas are all considered as independent scenarios. Let be the standardized performance metric of the headphones in the j-th interference environment scenario. This metric is obtained by weighted fusion of multiple raw performance values ​​(such as signal stability, audio clarity, packet loss rate, etc.) and represents the performance level of the headphones in this scenario. These are standard performance values ​​for headphones under ideal, interference-free conditions, serving as a unified benchmark reference. These values ​​can be obtained through measurements taken under conditions where external interference is eliminated. This represents the response time required for the headphones to reach a stable performance state under the j-th interference environment. This value can be obtained by detecting the stability inflection point in the performance curve, reflecting the headphones' adaptability to environmental disturbances. This represents the response time under baseline conditions, serving as a reference point for time adaptability. k is a time sensitivity coefficient that adjusts the steepness of the exponential function; a larger k value indicates greater sensitivity to differences in response time. This parameter can be determined through model training or empirical settings.

[0080] In some embodiments, the test optimization module 206 is further configured to: Based on the performance bottleneck identification report, extract abnormal parameters from the link quality assessment data; Based on the abnormal parameters, the corresponding improvement scheme is matched in the preset optimization strategy library; The improved scheme is analyzed in conjunction with the interference adaptability index to generate optimization suggestion data.

[0081] In this embodiment, to optimize the performance of Bluetooth headsets in dynamic scenarios with multiple interferences, the system first analyzes the link quality assessment data collected in each test scenario based on the performance bottleneck identification report, identifying and extracting abnormal parameters. These abnormal parameters may include, but are not limited to: packet loss rate exceeding a preset threshold, retransmission rate continuously increasing, abnormal RSSI (Received Signal Strength Index) fluctuations, and SNR (Signal-to-Noise Ratio) below a critical value. The system automatically determines the key indicators causing performance degradation by comparing the data with the normal reference range using predefined anomaly identification rules.

[0082] Next, based on the extracted abnormal parameters, the system matches them against a pre-defined optimization strategy library. This library contains multiple predefined intervention strategies and their matching conditions, specifically including: adjusting the Bluetooth channel, switching audio encoding protocols (e.g., switching from SBC to AAC or aptX), modifying the buffer queue length, and dynamically reducing the bit rate to lower link load. The system then uses a parameter feature matching algorithm to select several candidate improvement schemes that best match the current abnormal pattern.

[0083] Furthermore, to improve the adaptability and accuracy of the optimization schemes, the system performs joint analysis of the aforementioned candidate improvement schemes with the previously calculated Interference Adaptability Index (IAI). This analysis process includes: using the historical optimization effects of each improvement scheme in different IAI ranges as reference weights, and dynamically adjusting the priority and application conditions of the optimization suggestions in conjunction with the current IAI value, thereby generating a set of optimization suggestion data. This data specifically points to the most suitable strategy combination for the current headphones to implement in this scenario.

[0084] Ultimately, the optimized suggestion data can be used for subsequent control policy updates, firmware upgrade suggestions, or user-level prompts on the device side, thereby achieving proactive improvement in anti-interference capabilities and dynamic enhancement of link performance.

[0085] In some embodiments, the system further includes: A full-band signal acquisition module for capturing Bluetooth communication signals in the 2.4GHz and 5GHz frequency bands; The real-time decoding module is used to extract data packet loss rate, frequency hopping behavior and signal strength change information from Bluetooth communication signals. The comparative analysis module is used to compare the decoding results with benchmark performance indicators and output link quality assessment data.

[0086] The full-band signal acquisition module is configured to scan and capture communication signals between Bluetooth headsets and paired devices in real time within the 2.4GHz and 5GHz frequency bands. Through collaborative operation between the broadband RF front-end and the spectrum sensing unit, the module can: achieve accurate tracking of frequency-hopping spread spectrum characteristics; support parallel acquisition of communication signals under different Bluetooth protocols (such as BLE, BR / EDR); and continuously record channel usage distribution and collision events in dynamic interference environments.

[0087] By deploying this module, the spectrum occupancy of the headphones under various scenarios can be comprehensively reflected, providing basic signal data for subsequent link evaluation.

[0088] The real-time decoding module performs high-speed demodulation and protocol parsing operations based on the captured raw Bluetooth communication signal, extracting key parameters reflecting the stability of the communication link. This includes: 1. Packet Loss Rate: Evaluates communication integrity by calculating the ratio of packet loss during transmission to the total number of transmissions. 2. Frequency Hopping Dynamics: Track the changing patterns of frequency hopping sequences and analyze whether there are anomalies such as frequency congestion or conflicting frequency hopping; 3. Signal Strength Change Information (RSSI Trace): Extracts received signal strength (RSSI) in real time and analyzes its fluctuation range within a unit of time to identify physical layer interference.

[0089] The module adopts a hardware and software co-structure to ensure real-time, low-latency decoding and analysis without affecting link communication.

[0090] The comparative analysis module evaluates the current communication quality based on the link performance data output by the real-time decoding module, combined with the system's preset benchmark performance indicator model. Specifically, this includes: The extracted packet loss rate, frequency jump behavior, and signal strength fluctuation were compared with the baseline values ​​measured under a standard interference-free environment. A weighted scoring mechanism is used to calculate the quality change of the link; Output comprehensive link quality assessment data, including instantaneous stability score, frequency hopping behavior offset index, RSSI fluctuation coefficient, etc.

[0091] The output of this module will serve as an important input for interference perception analysis and optimization suggestion generation, providing decision support for achieving adaptive anti-interference performance optimization and loop adjustment.

[0092] Through the coordinated operation of the above modules, this embodiment can accurately reproduce the actual performance of the Bluetooth headset communication link under various typical interference scenarios, providing a reliable basis for subsequent interference adaptive modeling and system optimization.

[0093] In some embodiments, the bionic human model is also used for: A conductive framework structure that simulates the electromagnetic properties of human tissue; Simulates micro-movements of the human head, hand touch control, and full-body movement; A sensor array that collects motion data and signal absorption and reflection information in real time.

[0094] In this embodiment, the bionic human model construction includes the following key structures and functional modules to achieve high-precision simulation and real-time acquisition of the dynamic disturbance characteristics of the human body: The biomimetic human body model features an internal skeletal structure made of highly conductive materials to simulate the electromagnetic properties of human tissue. This skeletal structure, covered with multiple layers of composite materials, possesses electrical conductivity and dielectric constant similar to human skin, muscles, and bones, enabling realistic simulation of the absorption and reflection effects of Bluetooth radio frequency signals. This structure helps to accurately reflect the shielding and scattering characteristics of the human body against wireless signals, enhancing the realism of anti-interference testing.

[0095] The model is equipped with a multi-degree-of-freedom actuation system, capable of simulating various typical human dynamic movements, including but not limited to: micro-head movements such as head shaking, nodding, and turning; hand touch actions such as touching headphones and operating a mobile phone; and full-body movement modes such as walking, running, and sitting-standing transitions. The motion actuators are controlled by preset motion sequences to achieve high-precision, highly repeatable dynamic motion simulation, facilitating the system's stable reproduction of the impact of human movement on Bluetooth signals in various scenarios.

[0096] The biomimetic model is equipped with multi-type sensor arrays deployed in key areas, including inertial measurement units (IMUs), electromagnetic field sensors, and displacement sensors, enabling real-time acquisition of motion state data and Bluetooth signal absorption and reflection information. The acquired data is uploaded to the central control system via a high-speed data acquisition and transmission module, providing fundamental data support for subsequent interference characteristic modeling and performance analysis.

[0097] Through the integration of the above structure and functions, the bionic human body model achieves accurate simulation of the interaction between the human body and Bluetooth signals in a dynamic multidimensional interference environment, which greatly improves the reliability and practical value of Bluetooth headset anti-interference performance testing.

[0098] Please see Figure 3 The present invention provides a flowchart of a Bluetooth headset anti-interference performance testing method, including the following steps: Step 301: Construct a multi-dimensional interference source matrix. Control multiple interference sources to dynamically deploy in three-dimensional space using a programmable robotic arm to form an electromagnetic interference environment with adjustable interference intensity and spatial distribution, and obtain initial interference environment parameters.

[0099] Step 302: Based on the initial interference environment parameters, construct an environmental acoustic characteristic simulation system. By adjusting the loudspeaker array and variable acoustic materials, simulate the acoustic noise characteristics of the usage environment and generate composite interference scene parameters.

[0100] Step 303: Based on the composite interference scenario parameters, control the bionic human model with human electromagnetic properties to perform preset dynamic actions, and collect the absorption and reflection data of Bluetooth signals by the bionic model in real time to extract the dynamic interference characteristics of the human body.

[0101] Step 304: Based on the aforementioned human dynamic interference characteristics, a non-invasive Bluetooth link quality monitoring system is used to collect link parameters in real time during Bluetooth communication, and the link parameters are compared with preset benchmark performance indicators to obtain link quality assessment data.

[0102] Step 305: Based on the link quality assessment data, call the deep learning-based audio quality assessment model to calculate the dynamic audio quality score and obtain the audio performance assessment result.

[0103] Step 306: Based on the audio performance evaluation results, calculate the interference adaptability index and output optimization suggestion data.

[0104] Please see Figure 4 , Figure 4 A schematic diagram illustrating an embodiment of the electronic device provided in this invention. For example... Figure 4 As shown, an embodiment of the present invention provides an electronic device 400, including a memory 410, a processor 420, and a computer program 411 stored in the memory 410 and executable on the processor 420. When the processor 420 executes the computer program 411, it performs the following steps: A multi-dimensional interference source matrix is ​​constructed, and multiple interference sources are dynamically deployed in three-dimensional space by a programmable robotic arm to form an electromagnetic interference environment with adjustable interference intensity and spatial distribution, and to obtain initial interference environment parameters. Based on the initial interference environment parameters, an environmental acoustic characteristic simulation system is constructed. By adjusting the loudspeaker array and variable acoustic materials, the acoustic noise characteristics of the usage environment are simulated to generate composite interference scene parameters. Based on the parameters of the composite interference scenario, the bionic human model with human electromagnetic properties is controlled to perform preset dynamic actions, and the absorption and reflection data of the bionic model to Bluetooth signals are collected in real time to extract the dynamic interference characteristics of the human body. Based on the aforementioned human dynamic interference characteristics, a non-invasive Bluetooth link quality monitoring system is used to collect link parameters in real time during Bluetooth communication, and the link parameters are compared with preset benchmark performance indicators to obtain link quality evaluation data. Based on the link quality assessment data, a deep learning-based audio quality assessment model is invoked to calculate the dynamic audio quality score and obtain the audio performance assessment result. Based on the audio performance evaluation results, the interference adaptability index is calculated, and optimization suggestion data is output.

[0105] Please see Figure 5 , Figure 5 This is a schematic diagram illustrating an embodiment of a computer-readable storage medium provided by an embodiment of the present invention. For example... Figure 5 As shown, this embodiment provides a computer-readable storage medium 500 on which a computer program 411 is stored. When the computer program 411 is executed by a processor, it performs the following steps: A multi-dimensional interference source matrix is ​​constructed, and multiple interference sources are dynamically deployed in three-dimensional space by a programmable robotic arm to form an electromagnetic interference environment with adjustable interference intensity and spatial distribution, and to obtain initial interference environment parameters. Based on the initial interference environment parameters, an environmental acoustic characteristic simulation system is constructed. By adjusting the loudspeaker array and variable acoustic materials, the acoustic noise characteristics of the usage environment are simulated to generate composite interference scene parameters. Based on the parameters of the composite interference scenario, the bionic human model with human electromagnetic properties is controlled to perform preset dynamic actions, and the absorption and reflection data of the bionic model to Bluetooth signals are collected in real time to extract the dynamic interference characteristics of the human body. Based on the aforementioned human dynamic interference characteristics, a non-invasive Bluetooth link quality monitoring system is used to collect link parameters in real time during Bluetooth communication, and the link parameters are compared with preset benchmark performance indicators to obtain link quality evaluation data. Based on the link quality assessment data, a deep learning-based audio quality assessment model is invoked to calculate the dynamic audio quality score and obtain the audio performance assessment result. Based on the audio performance evaluation results, the interference adaptability index is calculated, and optimization suggestion data is output.

[0106] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0107] Those skilled in the art will understand that embodiments of the present invention can be provided as systems, methods, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0108] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A system that specifies functions in one or more boxes.

[0109] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including an instruction set implemented in a process. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0110] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0111] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0112] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A Bluetooth headset anti-interference performance testing system, characterized in that, The system includes: The environmental parameter module is used to construct a multi-dimensional interference source matrix. It controls multiple interference sources to be dynamically deployed in three-dimensional space through a programmable robotic arm, forming an electromagnetic interference environment with adjustable interference intensity and spatial distribution, and obtaining initial interference environment parameters. The scene parameter module is used to construct an environmental acoustic characteristic simulation system based on the initial interference environment parameters. By adjusting the loudspeaker array and variable acoustic materials, it simulates the acoustic noise characteristics of the usage environment and generates composite interference scene parameters. The feature extraction module is used to control a bionic human model with human electromagnetic properties to perform preset dynamic actions based on the parameters of the composite interference scenario, and to collect data on the absorption and reflection of Bluetooth signals by the bionic model in real time to extract human dynamic interference features. The link evaluation module is used to collect link parameters in real time during Bluetooth communication based on the human body dynamic interference characteristics using a non-invasive Bluetooth link quality monitoring system, and compare the link parameters with preset benchmark performance indicators to obtain link quality evaluation data. The audio evaluation module is used to call a deep learning-based audio quality evaluation model based on the link quality evaluation data to calculate a dynamic audio quality score and obtain audio performance evaluation results. The test optimization module is used to calculate the interference adaptability index based on the audio performance evaluation results and output optimization suggestion data.

2. The Bluetooth headset anti-interference performance testing system according to claim 1, characterized in that, The environmental parameter module is also used for: Based on the three-dimensional deployment location and emission parameters of each interference source, corresponding spatial distribution parameters are generated; Based on the operating frequency band characteristics and transmission power of the interference source, calculate the corresponding electromagnetic interference intensity parameters; The spatial distribution parameters and the electromagnetic interference intensity parameters are input into a preset interference superposition model, and the initial interference environment parameters are output.

3. The Bluetooth headset anti-interference performance testing system according to claim 2, characterized in that, The scene parameter module is also used for: Based on the initial interference environment parameters, the sound pressure level and frequency distribution of the loudspeaker array are controlled to generate traffic noise characteristic parameters; Based on the traffic noise characteristic parameters, acoustic environment parameters are generated by adjusting the acoustic reflection coefficient of the variable acoustic material. The traffic noise characteristic parameters and the acoustic environment parameters are input into the environmental noise superposition algorithm to output the composite interference scene parameters.

4. The Bluetooth headset anti-interference performance testing system according to claim 3, characterized in that, The feature extraction module is also used for: Based on a preset dynamic action sequence, motion data of a bionic human model is collected, and corresponding motion feature parameters are generated. The motion characteristic parameters are input into the conductivity model to calculate the absorption and reflection rates of Bluetooth signals by the human body. Based on the absorption rate and the reflectivity, the dynamic interference characteristics of the human body are output through a signal interference model.

5. The Bluetooth headset anti-interference performance testing system according to claim 4, characterized in that, The link evaluation module is also used for: The link parameters are collected in real time; Based on the link parameters, calculate the data packet loss rate and retransmission rate of the Bluetooth link; The packet loss rate and the retransmission rate are input into the link quality scoring model, and the link quality assessment data is output.

6. The Bluetooth headset anti-interference performance testing system according to claim 5, characterized in that, The audio evaluation module is also used for: Obtain a training dataset containing reference audio samples from normal environments and test audio samples from interfering environments. The deep learning model is trained based on the training dataset. During training, a preset loss function, including an error term for audio quality indicators and a jitter penalty term, is used to optimize the model parameters to obtain the dynamic audio quality score.

7. The Bluetooth headset anti-interference performance testing system according to claim 6, characterized in that, The test optimization module is also used for: Obtain performance metrics in various test scenarios; The performance indicators are normalized to generate standardized performance data; The standardized performance data is input into a time response model for calculation to obtain the interference adaptability index.

8. The Bluetooth headset anti-interference performance testing system according to claim 7, characterized in that, The test optimization module is also used for: Based on the performance bottleneck identification report, extract the abnormal parameters from the link quality assessment data; Based on the abnormal parameters, a corresponding improvement scheme is matched in the preset optimization strategy library; The improved scheme is combined with the interference adaptability index to generate the optimization suggestion data.

9. The Bluetooth headset anti-interference performance testing system according to claim 8, characterized in that, The system also includes: A full-band signal acquisition module for capturing Bluetooth communication signals in the 2.4GHz and 5GHz frequency bands; The real-time decoding module is used to extract data packet loss rate, frequency hopping behavior and signal strength change information from the Bluetooth communication signal; The comparative analysis module is used to compare the decoding results with benchmark performance indicators and output the link quality assessment data.

10. The Bluetooth headset anti-interference performance testing system according to claim 9, characterized in that, The bionic human model is also used for: A conductive framework structure that simulates the electromagnetic properties of human tissue; Simulates micro-movements of the human head, hand touch control, and full-body movement; A sensor array that collects motion data and signal absorption and reflection information in real time.

Images